paaniyan/dpo-qwen-cot-merged

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 13, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The paaniyan/dpo-qwen-cot-merged model is a 4 billion parameter Qwen3-based instruction-tuned causal language model. It was fine-tuned using Direct Preference Optimization (DPO) with the Unsloth library to enhance reasoning capabilities, specifically Chain-of-Thought (CoT), and improve structured response quality. This model is optimized for tasks requiring advanced reasoning and coherent, structured outputs.

Loading preview...

Model Overview

This model, paaniyan/dpo-qwen-cot-merged, is a 4 billion parameter variant of the Qwen3-4B-Instruct-2507 base model. It has undergone Direct Preference Optimization (DPO) using the Unsloth library, resulting in a full-merged 16-bit weight model that requires no adapter loading.

Key Capabilities

  • Enhanced Reasoning: Optimized specifically to improve Chain-of-Thought (CoT) reasoning, making it suitable for complex problem-solving.
  • Structured Response Quality: Fine-tuned to produce more coherent and structured outputs based on preferred response patterns.
  • Direct Use: As a fully merged model, it can be used directly with the transformers library for inference.

Training Details

The model was trained for 1 epoch with a learning rate of 1e-07 and a beta value of 0.1, using a maximum sequence length of 1024. The training data utilized was u-10bei/dpo-dataset-qwen-cot. The model is released under the MIT License, with users also required to comply with the original base model's license terms.

Good For

  • Applications requiring improved logical reasoning and step-by-step thought processes.
  • Generating structured and high-quality text responses.
  • Developers seeking a Qwen3-based model with enhanced DPO alignment for reasoning tasks.